메뉴 건너뛰기




Volumn 10, Issue 4, 1997, Pages 721-735

Premature saturation in backpropagation networks: Mechanism and necessary conditions

Author keywords

Backpropagation training algorithm; Feedforward neural networks; Flat spot; Necessary conditions; Premature saturation

Indexed keywords

PREMATURE SATURATION;

EID: 0031171576     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00117-7     Document Type: Article
Times cited : (55)

References (12)
  • 1
    • 0007486259 scopus 로고
    • Improving convergence of back-propagation by handling flat-spots in the output layer
    • I. Aleksander & J. Taylor (Eds.), Elsevier Science: North-Holland
    • Balakrishnan, K., & Honavar, V. (1992). Improving convergence of back-propagation by handling flat-spots in the output layer. In I. Aleksander & J. Taylor (Eds.), Proceedings of the International Conference on Artificial Neural Networks: Vol. 2 (pp. 1003-1009). Elsevier Science: North-Holland.
    • (1992) Proceedings of the International Conference on Artificial Neural Networks , vol.2 , pp. 1003-1009
    • Balakrishnan, K.1    Honavar, V.2
  • 2
    • 0003940119 scopus 로고
    • Stepsize variation methods for accelerating the back-propagation algorithm
    • M. Caudill (Ed.), Piscataway, NJ: IEEE Neural Networks Council
    • Chen, J.R., & Mars, P. (1990). Stepsize variation methods for accelerating the back-propagation algorithm. In M. Caudill (Ed.), Proceedings of the International Joint Conference on Neural Networks: Vol. I (pp. 601-604). Piscataway, NJ: IEEE Neural Networks Council.
    • (1990) Proceedings of the International Joint Conference on Neural Networks , vol.1 , pp. 601-604
    • Chen, J.R.1    Mars, P.2
  • 3
    • 0023540352 scopus 로고
    • Accelerated learning using the generalized delta rule
    • M. Caudill & C.B. Butler (Eds.), Piscataway. NJ: SOS Printing
    • Dahl, E.D. (1987). Accelerated learning using the generalized delta rule. In M. Caudill & C.B. Butler (Eds.), Proceedings of the International Joint Conference on Neural Networks: Vol. II (pp. 523-530). Piscataway. NJ: SOS Printing.
    • (1987) Proceedings of the International Joint Conference on Neural Networks , vol.2 , pp. 523-530
    • Dahl, E.D.1
  • 4
    • 0003000735 scopus 로고
    • Faster-Learning Variations on back-propagation: An empirical study
    • D. Touretzky, G. Hinten, & T. Sejnowski (Eds.), San Mateo, CA: Morgan Kaufmann
    • Fahlman, S.E. (1989). Faster-Learning Variations on back-propagation: an empirical study. In D. Touretzky, G. Hinten, & T. Sejnowski (Eds.), Proceedings of the Connectionist Models Summer School (pp. 38-51). San Mateo, CA: Morgan Kaufmann.
    • (1989) Proceedings of the Connectionist Models Summer School , pp. 38-51
    • Fahlman, S.E.1
  • 6
    • 0026376527 scopus 로고
    • The effect of initial weights on premature saturation in back-propagation training
    • Piscataway, NJ: IEEE Neural Networks Council
    • Lee, Y., Oh, S.H., & Kim, M.W. ( 1991 ). The effect of initial weights on premature saturation in back-propagation training. In Proceedings of the International Joint Conference on Neural Networks: Vol. II (pp. 765-770). Piscataway, NJ: IEEE Neural Networks Council.
    • (1991) Proceedings of the International Joint Conference on Neural Networks , vol.2 , pp. 765-770
    • Lee, Y.1    Oh, S.H.2    Kim, M.W.3
  • 7
    • 0027878882 scopus 로고
    • An empirical comparison of flat-spot elimination techniques in back-propagation networks
    • M.L. Padgett (Ed.), San Diego, CA: Society for Computer Simulation
    • Parekh, R., Balakrishnan, K., & Honavar, V. (1993). An empirical comparison of flat-spot elimination techniques in back-propagation networks. In M.L. Padgett (Ed.), Proceedings of the Third Workshop on Neural Networks: Academic/Industrial/NASA/Defense (pp. 55-60). San Diego, CA: Society for Computer Simulation.
    • (1993) Proceedings of the Third Workshop on Neural Networks: Academic/Industrial/NASA/Defense , pp. 55-60
    • Parekh, R.1    Balakrishnan, K.2    Honavar, V.3
  • 8
    • 0028439190 scopus 로고
    • Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications
    • Reifman, J., & Vitela, J.E. (1994). Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications. Nuclear Technology, 106, 225-241.
    • (1994) Nuclear Technology , vol.106 , pp. 225-241
    • Reifman, J.1    Vitela, J.E.2
  • 12
    • 0141759457 scopus 로고
    • Enhanced backpropagation training algorithm for transient event identification
    • Vitela, J.E., & Reifman, J. (1993). Enhanced backpropagation training algorithm for transient event identification. Transactions of the American Nuclear Society, 69, 148-149.
    • (1993) Transactions of the American Nuclear Society , vol.69 , pp. 148-149
    • Vitela, J.E.1    Reifman, J.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.